Update app.py

app.py

@@ -1,80 +1,44 @@
-from pyexpat.errors import messages
 import gradio as gr
-from huggingface_hub import InferenceClient
-import spaces
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-@spaces.GPU
-
-
+import requests
+import os
+import spaces 
 
 
-
-
-    
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    
+API_URL = "https://api-inference.huggingface.co/models/meta-llama/Meta-Llama-3-8B-Instruct"
+api_token = os.environ.get("TOKEN")
+headers = {"Authorization": f"Bearer {api_token}"}
+@spaces.GPU
+def query(payload):
+    response = requests.post(API_URL, headers=headers, json=payload)
+    return response.json()
+
+def generate_response(prompt):
+    payload = {
+        "inputs": prompt,
+        "parameters": {
+            "max_new_tokens": 100,
+            "temperature": 0.7,
+            "top_p": 0.95,
+            "do_sample": True
+        }
+    }
     
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""        
-
+    response = query(payload)
     
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-
-        ),
-    ],
-
+    if isinstance(response, list) and len(response) > 0:
+        return response[0].get('generated_text', '')
+    elif isinstance(response, dict) and 'generated_text' in response:
+        return response['generated_text']
+    return "Désolé, je n'ai pas pu générer de réponse."
+
+def chatbot(message, history):
+    response = generate_response(message)
+    return response
+
+iface = gr.ChatInterface(
+    fn=chatbot,
+    title="Chatbot Meta-Llama-3-8B-Instruct",
+    description="Interagissez avec le modèle Meta-Llama-3-8B-Instruct."
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+iface.launch()